第一个Tensorflow例子

第一个Tensorflow例子

程序:

import tensorflow as tf
import numpy as np

#create data
x_data=np.random.rand(100).astype(np.float32)
y_data=x_data*0.1+0.3

#create tensorflow structure start
Weights=tf.Variable(tf.random_uniform([1],-1.0,1.0))
biases=tf.Variable(tf.zeros([1]))

y=Weights*x_data+biases

loss=tf.reduce_mean(tf.square(y-y_data))
optimizer=tf.train.GradientDescentOptimizer(0.5)
train=optimizer.minimize(loss)

#init=tf.initialize_all_variables()
init=tf.global_variables_initializer()
##create tensorflow structure end

sess=tf.Session()
sess.run(init)

for step in range(401):
sess.run(train)
if step%5==0:
print(step,sess.run(Weights),sess.run(biases))

sess.close()

运行结果:

(0, array([0.67580247], dtype=float32), array([-0.01624661], dtype=float32))
(5, array([0.51550275], dtype=float32), array([0.079072], dtype=float32))
(10, array([0.3976643], dtype=float32), array([0.14171882], dtype=float32))
(15, array([0.31324816], dtype=float32), array([0.18660662], dtype=float32))
(20, array([0.25277203], dtype=float32), array([0.21876444], dtype=float32))
(25, array([0.20944662], dtype=float32), array([0.24180244], dtype=float32))
(30, array([0.17840809], dtype=float32), array([0.25830698], dtype=float32))
(35, array([0.15617192], dtype=float32), array([0.27013093], dtype=float32))
(40, array([0.14024183], dtype=float32), array([0.27860168], dtype=float32))
(45, array([0.12882945], dtype=float32), array([0.28467014], dtype=float32))
(50, array([0.12065355], dtype=float32), array([0.28901762], dtype=float32))
(55, array([0.11479631], dtype=float32), array([0.29213217], dtype=float32))
(60, array([0.11060014], dtype=float32), array([0.29436344], dtype=float32))
(65, array([0.10759401], dtype=float32), array([0.29596195], dtype=float32))
(70, array([0.10544039], dtype=float32), array([0.29710713], dtype=float32))
(75, array([0.10389752], dtype=float32), array([0.29792753], dtype=float32))
(80, array([0.1027922], dtype=float32), array([0.2985153], dtype=float32))
(85, array([0.10200034], dtype=float32), array([0.29893634], dtype=float32))
(90, array([0.10143306], dtype=float32), array([0.299238], dtype=float32))
(95, array([0.10102665], dtype=float32), array([0.2994541], dtype=float32))
(100, array([0.1007355], dtype=float32), array([0.29960892], dtype=float32))
(105, array([0.10052691], dtype=float32), array([0.29971984], dtype=float32))
(110, array([0.10037749], dtype=float32), array([0.2997993], dtype=float32))
(115, array([0.10027044], dtype=float32), array([0.29985622], dtype=float32))
(120, array([0.10019374], dtype=float32), array([0.299897], dtype=float32))
(125, array([0.1001388], dtype=float32), array([0.2999262], dtype=float32))
(130, array([0.10009945], dtype=float32), array([0.29994714], dtype=float32))
(135, array([0.10007126], dtype=float32), array([0.29996213], dtype=float32))
(140, array([0.10005105], dtype=float32), array([0.29997286], dtype=float32))
(145, array([0.10003658], dtype=float32), array([0.29998055], dtype=float32))
(150, array([0.10002621], dtype=float32), array([0.29998606], dtype=float32))
(155, array([0.10001878], dtype=float32), array([0.29999003], dtype=float32))
(160, array([0.10001346], dtype=float32), array([0.29999286], dtype=float32))
(165, array([0.10000965], dtype=float32), array([0.2999949], dtype=float32))
(170, array([0.10000692], dtype=float32), array([0.29999635], dtype=float32))
(175, array([0.10000495], dtype=float32), array([0.2999974], dtype=float32))
(180, array([0.10000355], dtype=float32), array([0.29999813], dtype=float32))
(185, array([0.10000254], dtype=float32), array([0.29999867], dtype=float32))
(190, array([0.10000183], dtype=float32), array([0.29999906], dtype=float32))
(195, array([0.1000013], dtype=float32), array([0.29999933], dtype=float32))
(200, array([0.10000094], dtype=float32), array([0.2999995], dtype=float32))
(205, array([0.10000069], dtype=float32), array([0.29999965], dtype=float32))
(210, array([0.10000049], dtype=float32), array([0.29999974], dtype=float32))
(215, array([0.10000036], dtype=float32), array([0.29999983], dtype=float32))
(220, array([0.10000025], dtype=float32), array([0.2999999], dtype=float32))
(225, array([0.10000018], dtype=float32), array([0.29999992], dtype=float32))
(230, array([0.10000013], dtype=float32), array([0.29999995], dtype=float32))
(235, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(240, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(245, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(250, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(255, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(260, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(265, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(270, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(275, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(280, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(285, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(290, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(295, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(300, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(305, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(310, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(315, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(320, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(325, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(330, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(335, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(340, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(345, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(350, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(355, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(360, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(365, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(370, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(375, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(380, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(385, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(390, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(395, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))
(400, array([0.1000001], dtype=float32), array([0.29999995], dtype=float32))

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值